© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21625
    Prev
    Next
    INDEX
    Explanations

    literally followed by emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĸ°æĿIJ
    -0.07
    æ³ĵ
    -0.07
     Huss
    -0.07
    áĥªáĥĺ
    -0.07
    inari
    -0.06
    ç´¢èı²
    -0.06
     alun
    -0.06
    ç´ł
    -0.06
    æľªçŁ¥çļĦ
    -0.06
    ×ŀ×ķת
    -0.06
    POSITIVE LOGITS
    åģļåĪ°äºĨ
    0.11
    羣æŃ£æĦıä¹īä¸ĬçļĦ
    0.11
     truly
    0.10
    æĦıä¹īä¸ĬçļĦ
    0.10
    åģļåĪ°
    0.10
    åIJįåī¯åħ¶å®ŀçļĦ
    0.10
    çļĦ羣æŃ£
    0.09
     Truly
    0.09
    称å¾Ĺä¸Ĭ
    0.09
    羣æŃ£åģļåĪ°
    0.08
    Activations Density 0.274%

    No Known Activations